Skip to main content ->
Ai2

Research - Papers

Explore a selection of our published work on a variety of key research challenges in AI.

Filter papers

MolmoAct2: Action Reasoning Models for Real-world Deployment

Haoquan FangJiafei DuanD. ClayRanjay Krishna
2026
CoRL

Vision-Language-Action (VLA) models aim to provide a single generalist controller for robots, but today's systems fall short on the criteria that matter for real-world deployment. Frontier models… 

MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation

Abhay DeshpandeM. GuruRose HendrixRanjay Krishna
2026
CoRL, ICRA • SDRL Workshop, ICRA • VLA Pipeline Workshop, ICRA • Beyond Teleoperation Workshop

A prevailing view in robot learning is that simulation alone is not enough; effective sim-to-real transfer is widely believed to require at least some real-world data collection or task-specific… 

TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation

Dongwon SonFlorian ShkurtiJason LeeDieter Fox
2026
CoRL

A policy tuned for one robot often behaves differently on another, whether due to the sim-to-real gap, unknown payloads, or the differing dynamics of two instances of the same robot. In… 

VLS: Steering Pretrained Robot Policies via Vision-Language Models

Shuo LiuIshneet Sukhvinder SinghYiqing XuRanjay Krishna
2026
CoRL, CVPR • 3D-LLM/VLA Workshop, CVPR • Foundation Models Meet Embodied Agents Workshop

Why do pretrained diffusion or flow-matching policies fail when the same task is performed near an obstacle, on a shifted support surface, or amid mild clutter? Such failures rarely reflect missing… 

HARPA: A Testability-Driven, Literature-Grounded Framework for Research Ideation

Rosni VasuPeter JansenPao SiangliulueBhavana Dalvi
2026
AACL-IJCNLP 2026

While there has been a surge of interest in automated scientific discovery (ASD), especially with the emergence of LLMs, it remains challenging for tools to generate hypotheses that are both… 

LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape

Hita KambhamettuBhavana Dalvi MishraAndrew HeadPao Siangliulue
2026
UIST 2026

Developing a novel research idea is hard. It must be distinct enough from prior work to claim a contribution while also building on it. This requires iteratively reviewing literature and refining an… 

Context-Aware RL for Agentic and Multimodal LLMs

Peiyang XuBangzheng LiSijia LiuXingyu Fu
2026
COLM • Efficient Reasoning (spotlight)

Large language models (LLMs) often fail when answering requires identifying a small but decisive piece of evidence within a long or complex context, such as a single line in a tool trace or a subtle… 

Cracks in the Foundation: Seemingly Minor Architectural Choices Impact Long Context Extension

Amanda BertschLuca SoldainiMatthew R. GormleyD. Groeneveld
2026
COLM

One might imagine that architectural variations within the dense transformer paradigm have a limited effect on accuracy. However, we demonstrate that this is not the case in the long context… 

Olmo Hybrid: From Theory to Practice and Back

William MerrillYanhong LiTyler RomeroAshish Sabharwal
2026
COLM

Recent work has demonstrated the potential of non-transformer language models, especially linear recurrent neural networks (RNNs) and hybrid models that mix recurrence and attention. Yet there is no… 

FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Models

Zijun LinJiafei DuanHaoquan FangBihan Wen
2026
IROS

Recent advances in robotic manipulation have integrated low-level robotic control into Vision-Language Models (VLMs), extending them into Vision-Language-Action (VLA) models. Although… 

1-10Next